{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QZOS2VH2JDLI7CH54MKGGDCU5T","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"269efe0b3110d365a989cbeef467753a0f0316020ce9b2a8167431d1bf6b73be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T17:53:23Z","title_canon_sha256":"e28cc7493ce4830af8649b777d34864c5f1de4b5794b40a6fd0bb4e44d47216d"},"schema_version":"1.0","source":{"id":"2503.13423","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13423","created_at":"2026-07-05T11:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13423v3","created_at":"2026-07-05T11:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13423","created_at":"2026-07-05T11:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"QZOS2VH2JDLI","created_at":"2026-07-05T11:59:41Z"},{"alias_kind":"pith_short_16","alias_value":"QZOS2VH2JDLI7CH5","created_at":"2026-07-05T11:59:41Z"},{"alias_kind":"pith_short_8","alias_value":"QZOS2VH2","created_at":"2026-07-05T11:59:41Z"}],"graph_snapshots":[{"event_id":"sha256:0cb259dd5e79c6fef6bf773b42187c43b096825690ccb53dee45892a974ddc90","target":"graph","created_at":"2026-07-05T11:59:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.13423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The assumption across nearly all language model (LM) tokenization schemes is that tokens should be subwords, i.e., contained within word boundaries. While providing a seemingly reasonable inductive bias, is this common practice limiting the potential of modern LMs? Whitespace is not a reliable delimiter of meaning, as evidenced by multi-word expressions (e.g., \"by the way\"), crosslingual variation in the number of words needed to express a concept (e.g., \"spacesuit helmet\" in German is \"raumanzughelm\"), and languages that do not use whitespace at all (e.g., Chinese). To explore the potential o","authors_text":"Alisa Liu, Jonathan Hayase, Noah A. Smith, Sewoong Oh, Valentin Hofmann, Yejin Choi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T17:53:23Z","title":"SuperBPE: Space Travel for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13423","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e1390bc6edcf338a2308f5b79de2ca766851c1615f304bc363e2418ec00787aa","target":"record","created_at":"2026-07-05T11:59:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"269efe0b3110d365a989cbeef467753a0f0316020ce9b2a8167431d1bf6b73be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T17:53:23Z","title_canon_sha256":"e28cc7493ce4830af8649b777d34864c5f1de4b5794b40a6fd0bb4e44d47216d"},"schema_version":"1.0","source":{"id":"2503.13423","kind":"arxiv","version":3}},"canonical_sha256":"865d2d54fa48d68f88fde314630c54ecdaf827dc67d79598e1b694fd006b1e01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"865d2d54fa48d68f88fde314630c54ecdaf827dc67d79598e1b694fd006b1e01","first_computed_at":"2026-07-05T11:59:41.007704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:41.007704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YbjAvNCugpADAcJXlEEI9MRrLaf0gr3i+ZfHVHRqKz7UkpdghSJGIhOa0B05VWc/NcZ35cH5VUvocSCCS4mBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:41.008179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13423","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1390bc6edcf338a2308f5b79de2ca766851c1615f304bc363e2418ec00787aa","sha256:0cb259dd5e79c6fef6bf773b42187c43b096825690ccb53dee45892a974ddc90"],"state_sha256":"82b0c675469ab9887525e98297aba0ffc96aecc5386cba00de9b5f852e1a75ed"}